Title Predicting Calls: New Service for an Intelligent Phone
Publication Type Conference Paper
Year of Publication 2007
Authors Phithakkitnukoon, S, Dantu, R
Conference Name 10th IFIP/IEEE International Conference on Management of Multimedia and Mobile Networks and Services, MMNS 2007
Date Published 11/2007
Conference Location San José, USA
Keywords Arrival time, behavior, call matrix, Callee, Caller, Communications, Incoming calls, Inter-arrival time, Inter-arrival/departure time, Kernel density estimation, Outgoing calls, Probability density function (pdf), Receiving call probability, Reciprocity
Abstract

Predicting future calls can be the next advanced feature of the intelligent phone as the phone service providers are looking to offer new services to their customers. Call prediction can be useful to many applications such as planning daily schedule and attending unwanted communications (e.g. voice spam). Predicting calls is a very challenging task. We believe that this is a new area of research. In this paper, we propose a Call Predictor (CP) that computes the probability of receiving calls and makes call prediction based on caller's behavior and reciprocity. The proposed call predictor is tested with the actual call logs. The experimental results show that the call predictor performs reasonably well with false positive rate of 2.4416%, false negative rate of 2.9191%, and error rate of 5.3606%.

DOI 10.1007/978-3-540-75869-3\_3

UNT Department:

UNT Center:

UNT Lab: